We have architected and evaluated a new kind of data resource, one that is composed of a logical collection of ephemeral data streams that could be viewed as a collection of publi...
Scalable atomic and parallel access to noncontiguous regions of a file is essential to exploit high performance I/O as required by large-scale applications. Parallel I/O framewor...
Peter M. Aarestad, Avery Ching, George K. Thiruvat...
We present a transparent, system-level checkpointing solution for master-worker parallelism that automatically adapts, upon restart, to the number of processor nodes available. Th...
Abstract— An efficient, accurate and distributed metadataoriented prefetching scheme is critical to the overall performance in large distributed storage systems. In this paper, ...
—Job monitoring in Grid systems presents an important challenge due to Grid environments are volatile, heterogeneous, not reliable and are managed by different middlewares and mo...